Neural Network-Based Transceiver Design for VLC System over ISI Channel

In this letter, we construct the neural network (NN)-based transceiver to compensate for the varying inter-symbol-interference (ISI) effect in visible light communication (VLC) systems. For processing variable-length sequences, the convolution neural network (CNN) is utilized, and then the residual...

Full description

Bibliographic Details
Main Authors: Lin Li, Zhaorui Zhu, Jian Zhang
Format: Article
Language:English
Published: MDPI AG 2022-03-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/9/3/190
_version_ 1797443529555836928
author Lin Li
Zhaorui Zhu
Jian Zhang
author_facet Lin Li
Zhaorui Zhu
Jian Zhang
author_sort Lin Li
collection DOAJ
description In this letter, we construct the neural network (NN)-based transceiver to compensate for the varying inter-symbol-interference (ISI) effect in visible light communication (VLC) systems. For processing variable-length sequences, the convolution neural network (CNN) is utilized, and then the residual network structure is further leveraged at the receiver part to enhance the performance. To cope with varying ISI, the pilot sequence, instead of channel side information (CSI) obtained by an additional module, is integrated into the framework to recover the data sequence directly. Simulation results show that the symbol error rate (SER) performance of the proposed NN-based transceiver can outperform separately designed transceiver schemes and approach the ideal perfect CSI (PCSI) case with a few pilot symbols or even no pilot.
first_indexed 2024-03-09T12:57:23Z
format Article
id doaj.art-ef23fb6b130c447a893c907b952834dd
institution Directory Open Access Journal
issn 2304-6732
language English
last_indexed 2024-03-09T12:57:23Z
publishDate 2022-03-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj.art-ef23fb6b130c447a893c907b952834dd2023-11-30T21:59:27ZengMDPI AGPhotonics2304-67322022-03-019319010.3390/photonics9030190Neural Network-Based Transceiver Design for VLC System over ISI ChannelLin Li0Zhaorui Zhu1Jian Zhang2National Digital Switching System Engineering and Technological Research Center, Zhengzhou 450000, ChinaNational Digital Switching System Engineering and Technological Research Center, Zhengzhou 450000, ChinaNational Digital Switching System Engineering and Technological Research Center, Zhengzhou 450000, ChinaIn this letter, we construct the neural network (NN)-based transceiver to compensate for the varying inter-symbol-interference (ISI) effect in visible light communication (VLC) systems. For processing variable-length sequences, the convolution neural network (CNN) is utilized, and then the residual network structure is further leveraged at the receiver part to enhance the performance. To cope with varying ISI, the pilot sequence, instead of channel side information (CSI) obtained by an additional module, is integrated into the framework to recover the data sequence directly. Simulation results show that the symbol error rate (SER) performance of the proposed NN-based transceiver can outperform separately designed transceiver schemes and approach the ideal perfect CSI (PCSI) case with a few pilot symbols or even no pilot.https://www.mdpi.com/2304-6732/9/3/190visible light communication (VLC)neural network (NN)deep learningautoencoder (AE)transceiver design
spellingShingle Lin Li
Zhaorui Zhu
Jian Zhang
Neural Network-Based Transceiver Design for VLC System over ISI Channel
Photonics
visible light communication (VLC)
neural network (NN)
deep learning
autoencoder (AE)
transceiver design
title Neural Network-Based Transceiver Design for VLC System over ISI Channel
title_full Neural Network-Based Transceiver Design for VLC System over ISI Channel
title_fullStr Neural Network-Based Transceiver Design for VLC System over ISI Channel
title_full_unstemmed Neural Network-Based Transceiver Design for VLC System over ISI Channel
title_short Neural Network-Based Transceiver Design for VLC System over ISI Channel
title_sort neural network based transceiver design for vlc system over isi channel
topic visible light communication (VLC)
neural network (NN)
deep learning
autoencoder (AE)
transceiver design
url https://www.mdpi.com/2304-6732/9/3/190
work_keys_str_mv AT linli neuralnetworkbasedtransceiverdesignforvlcsystemoverisichannel
AT zhaoruizhu neuralnetworkbasedtransceiverdesignforvlcsystemoverisichannel
AT jianzhang neuralnetworkbasedtransceiverdesignforvlcsystemoverisichannel